🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the NVIDIA GeForce RTX 3080 10GB run ERNIE-Doc Base (151M, WT103)?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE-Doc Base (151M, WT103) on the NVIDIA GeForce RTX 3080 10GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 113k | 1837.1-2189.4 t/s | ~96.7-115.2 (slow) |
| Q8 | yes | 115k | 3674.2-4378.8 t/s | ~193.4-230.5 (slow) |
| Q4 | yes | 116k | 6561-7819.3 t/s | ~345.3-411.5 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
→ All models on the NVIDIA GeForce RTX 3080 10GB
→ ERNIE-Doc Base (151M, WT103) specs
→ Other hardware
FAQ
Can the NVIDIA GeForce RTX 3080 10GB run ERNIE-Doc Base (151M, WT103)?▶
Yes. At Q4 it generates ~6561-7819.3 tok/s and fits up to 116k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~345.3-411.5 tok/s.
How much context fits?▶
At Q4, up to about 116k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.